{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:20:24Z","timestamp":1757618424745,"version":"3.44.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031959103"},{"type":"electronic","value":"9783031959110"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-95911-0_2","type":"book-chapter","created":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T06:07:36Z","timestamp":1750486056000},"page":"16-29","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Addressing Degeneracies in\u00a0Latent Interpolation for\u00a0Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6639-1257","authenticated-orcid":false,"given":"Erik","family":"Landolsi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9835-3020","authenticated-orcid":false,"given":"Fredrik","family":"Kahl","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,16]]},"reference":[{"key":"2_CR1","unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves imagenet classification. Trans. Mach. Learn. Res. (2023)"},{"key":"2_CR2","unstructured":"Balaji, Y., et\u00a0al.: ediffi: Text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"issue":"2","key":"2_CR3","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/502122.502124","volume":"20","author":"SR Buss","year":"2001","unstructured":"Buss, S.R., Fillmore, J.P.: Spherical averages and applications to spherical splines and interpolation. ACM Trans. Graphics (TOG) 20(2), 95\u2013126 (2001)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Chong, M.J., Forsyth, D.: Effectively unbiased fid and inception score and where to find them. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6070\u20136079 (2020)","DOI":"10.1109\/CVPR42600.2020.00611"},{"key":"2_CR5","unstructured":"Esser, P., et\u00a0al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"2_CR6","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: International Conference on Learning Representations (2023)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Garibi, D., Patashnik, O., Voynov, A., Averbuch-Elor, H., Cohen-Or, D.: Renoise: real image inversion through iterative noising. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-72630-9_23"},{"key":"2_CR8","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"2_CR9","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Jayasumana, S., Ramalingam, S., Veit, A., Glasner, D., Chakrabarti, A., Kumar, S.: Rethinking fid: Towards a better evaluation metric for image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9307\u20139315 (2024)","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"2_CR11","unstructured":"Khanna, S., et al.: Diffusionsat: a generative foundation model for satellite imagery. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"2_CR12","unstructured":"Landolsi, E., Kahl, F.: Tiny models from tiny data: textual and null-text inversion for few-shot distillation. arXiv preprint arXiv:2406.03146 (2024)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Lin, S., Liu, B., Li, J., Yang, X.: Common diffusion noise schedules and sample steps are flawed. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2024)","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"2_CR14","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: Learning to generate and transfer data with rectified flow. In: International Conference on Learning Representations (2023)"},{"key":"2_CR15","unstructured":"Meiri, B., Samuel, D., Darshan, N., Chechik, G., Avidan, S., Ben-Ari, R.: Fixed-point inversion for text-to-image diffusion models. arXiv preprint arXiv:2312.12540 (2023)"},{"key":"2_CR16","unstructured":"Miyake, D., Iohara, A., Saito, Y., Tanaka, T.: Negative-prompt inversion: fast image inversion for editing with text-guided diffusion models. arXiv preprint arXiv:2305.16807 (2023)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Pan, Z., Gherardi, R., Xie, X., Huang, S.: Effective real image editing with accelerated iterative diffusion inversion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 15912\u201315921 (2023)","DOI":"10.1109\/ICCV51070.2023.01458"},{"key":"2_CR19","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"2_CR20","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, pp. 234\u2013241, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2_CR23","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR24","unstructured":"Samuel, D., Ben-Ari, R., Darshan, N., Maron, H., Chechik, G.: Norm-guided latent space exploration for text-to-image generation. Adv. Neural Inform. Process. Syst. 36 (2024)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Sar\u0131y\u0131ld\u0131z, M.B., Alahari, K., Larlus, D., Kalantidis, Y.: Fake it till you make it: learning transferable representations from synthetic imagenet clones. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8011\u20138021 (2023)","DOI":"10.1109\/CVPR52729.2023.00774"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Shoemake, K.: Animating rotation with quaternion curves. In: The 12th Annual Conference on Computer Graphics and Interactive Techniques, pp. 245\u2013254 (1985)","DOI":"10.1145\/325334.325242"},{"key":"2_CR27","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021)"},{"key":"2_CR28","unstructured":"Trabucco, B., Doherty, K., Gurinas, M., Salakhutdinov, R.: Effective data augmentation with diffusion models. In: Proceedings of the International Conference of Learning Representations (2024)"},{"key":"2_CR29","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1109\/TMI.2012.2218117","volume":"32","author":"J Ul\u00e9n","year":"2013","unstructured":"Ul\u00e9n, J., Strandmark, P., Kahl, F.: An efficient optimization framework for multi-region segmentation based on lagrangian duality. IEEE Trans. Med. Imaging 32, 178\u2013188 (2013)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"2_CR30","unstructured":"Wang, Y., et al.: Infodiffusion: representation learning using information maximizing diffusion models. In: International Conference on Machine Learning. PMLR (2023)"},{"key":"2_CR31","unstructured":"Yang, Z., et al.: Impus: Image morphing with perceptually-uniform sampling using diffusion models. In: International Conference on Learning Representations (2024)"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhou, Y., Xu, X., Dai, B., Pan, X.: Diffmorpher: unleashing the capability of diffusion models for image morphing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7912\u20137921 (2024)","DOI":"10.1109\/CVPR52733.2024.00756"}],"container-title":["Lecture Notes in Computer Science","Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-95911-0_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T21:27:39Z","timestamp":1757194059000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-95911-0_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031959103","9783031959110"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-95911-0_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"16 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"SCIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Scandinavian Conference on Image Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Reykjavik","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Iceland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"scia2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/scia2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}